Merge tag 'pm-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:
 "These revert a recent change in the schedutil cpufreq governor that
  had not been expected to make any functional difference, but turned
  out to introduce a performance regression, fix an initialization issue
  in the amd-pstate driver and make it actually replace the venerable
  ACPI cpufreq driver on the supported systems by default.

  Specifics:

   - Revert a recent schedutil cpufreq governor change that introduced a
     performace regression on Pixel 6 (Sam Wu)

   - Fix amd-pstate driver initialization after running the kernel via
     kexec (Wyes Karny)

   - Turn amd-pstate into a built-in driver which allows it to take
     precedence over acpi-cpufreq by default on supported systems and
     amend it with a mechanism to disable this behavior (Perry Yuan)

   - Update amd-pstate documentation in accordance with the other
     changes made to it (Perry Yuan)"

* tag 'pm-6.1-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  Documentation: add amd-pstate kernel command line options
  Documentation: amd-pstate: add driver working mode introduction
  cpufreq: amd-pstate: add amd-pstate driver parameter for mode selection
  cpufreq: amd-pstate: change amd-pstate driver to be built-in type
  cpufreq: amd-pstate: cpufreq: amd-pstate: reset MSR_AMD_PERF_CTL register at init
  Revert "cpufreq: schedutil: Move max CPU capacity to sugov_policy"

2 files changed, 35 insertions, 16 deletions

diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 310779b07daf..00476e94db90 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -35,7 +35,7 @@ config X86_PCC_CPUFREQ
 	  If in doubt, say N.
 
 config X86_AMD_PSTATE
-	tristate "AMD Processor P-State driver"
+	bool "AMD Processor P-State driver"
 	depends on X86 && ACPI
 	select ACPI_PROCESSOR
 	select ACPI_CPPC_LIB if X86_64
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index ace7d50cf2ac..204e39006dda 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -59,12 +59,8 @@
  * we disable it by default to go acpi-cpufreq on these processors and add a
  * module parameter to be able to enable it manually for debugging.
  */
-static bool shared_mem = false;
-module_param(shared_mem, bool, 0444);
-MODULE_PARM_DESC(shared_mem,
-		 "enable amd-pstate on processors with shared memory solution (false = disabled (default), true = enabled)");
-
 static struct cpufreq_driver amd_pstate_driver;
+static int cppc_load __initdata;
 
 static inline int pstate_enable(bool enable)
 {
@@ -424,12 +420,22 @@ static void amd_pstate_boost_init(struct amd_cpudata *cpudata)
 	amd_pstate_driver.boost_enabled = true;
 }
 
+static void amd_perf_ctl_reset(unsigned int cpu)
+{
+	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
 	struct device *dev;
 	struct amd_cpudata *cpudata;
 
+	/*
+	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
+	 * which is ideal for initialization process.
+	 */
+	amd_perf_ctl_reset(policy->cpu);
 	dev = get_cpu_device(policy->cpu);
 	if (!dev)
 		return -ENODEV;
@@ -616,6 +622,15 @@ static int __init amd_pstate_init(void)
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		return -ENODEV;
+	/*
+	 * by default the pstate driver is disabled to load
+	 * enable the amd_pstate passive mode driver explicitly
+	 * with amd_pstate=passive in kernel command line
+	 */
+	if (!cppc_load) {
+		pr_debug("driver load is disabled, boot with amd_pstate=passive to enable this\n");
+		return -ENODEV;
+	}
 
 	if (!acpi_cpc_valid()) {
 		pr_warn_once("the _CPC object is not present in SBIOS or ACPI disabled\n");
@@ -630,13 +645,11 @@ static int __init amd_pstate_init(void)
 	if (boot_cpu_has(X86_FEATURE_CPPC)) {
 		pr_debug("AMD CPPC MSR based functionality is supported\n");
 		amd_pstate_driver.adjust_perf = amd_pstate_adjust_perf;
-	} else if (shared_mem) {
+	} else {
+		pr_debug("AMD CPPC shared memory based functionality is supported\n");
 		static_call_update(amd_pstate_enable, cppc_enable);
 		static_call_update(amd_pstate_init_perf, cppc_init_perf);
 		static_call_update(amd_pstate_update_perf, cppc_update_perf);
-	} else {
-		pr_info("This processor supports shared memory solution, you can enable it with amd_pstate.shared_mem=1\n");
-		return -ENODEV;
 	}
 
 	/* enable amd pstate feature */
@@ -653,16 +666,22 @@ static int __init amd_pstate_init(void)
 
 	return ret;
 }
+device_initcall(amd_pstate_init);
 
-static void __exit amd_pstate_exit(void)
+static int __init amd_pstate_param(char *str)
 {
-	cpufreq_unregister_driver(&amd_pstate_driver);
+	if (!str)
+		return -EINVAL;
 
-	amd_pstate_enable(false);
-}
+	if (!strcmp(str, "disable")) {
+		cppc_load = 0;
+		pr_info("driver is explicitly disabled\n");
+	} else if (!strcmp(str, "passive"))
+		cppc_load = 1;
 
-module_init(amd_pstate_init);
-module_exit(amd_pstate_exit);
+	return 0;
+}
+early_param("amd_pstate", amd_pstate_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");